linux-sg2042/net/bridge/br_device.c

418 lines
9.8 KiB
C
Raw Normal View History

/*
* Device handling code
* Linux ethernet bridge
*
* Authors:
* Lennert Buytenhek <buytenh@gnu.org>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/netpoll.h>
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
#include <linux/list.h>
#include <linux/netfilter_bridge.h>
#include <asm/uaccess.h>
#include "br_private.h"
#define COMMON_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | \
NETIF_F_GSO_MASK | NETIF_F_HW_CSUM)
const struct nf_br_ops __rcu *nf_br_ops __read_mostly;
EXPORT_SYMBOL_GPL(nf_br_ops);
bridge: fix lockdep addr_list_lock false positive splat After promisc mode management was introduced a bridge device could do dev_set_promiscuity from its ndo_change_rx_flags() callback which in turn can be called after the bridge's addr_list_lock has been taken (e.g. by dev_uc_add). This causes a false positive lockdep splat because the port interfaces' addr_list_lock is taken when br_manage_promisc() runs after the bridge's addr list lock was already taken. To remove the false positive introduce a custom bridge addr_list_lock class and set it on bridge init. A simple way to reproduce this is with the following: $ brctl addbr br0 $ ip l add l br0 br0.100 type vlan id 100 $ ip l set br0 up $ ip l set br0.100 up $ echo 1 > /sys/class/net/br0/bridge/vlan_filtering $ brctl addif br0 eth0 Splat: [ 43.684325] ============================================= [ 43.684485] [ INFO: possible recursive locking detected ] [ 43.684636] 4.4.0-rc8+ #54 Not tainted [ 43.684755] --------------------------------------------- [ 43.684906] brctl/1187 is trying to acquire lock: [ 43.685047] (_xmit_ETHER){+.....}, at: [<ffffffff8150169e>] dev_set_rx_mode+0x1e/0x40 [ 43.685460] but task is already holding lock: [ 43.685618] (_xmit_ETHER){+.....}, at: [<ffffffff815072a7>] dev_uc_add+0x27/0x80 [ 43.686015] other info that might help us debug this: [ 43.686316] Possible unsafe locking scenario: [ 43.686743] CPU0 [ 43.686967] ---- [ 43.687197] lock(_xmit_ETHER); [ 43.687544] lock(_xmit_ETHER); [ 43.687886] *** DEADLOCK *** [ 43.688438] May be due to missing lock nesting notation [ 43.688882] 2 locks held by brctl/1187: [ 43.689134] #0: (rtnl_mutex){+.+.+.}, at: [<ffffffff81510317>] rtnl_lock+0x17/0x20 [ 43.689852] #1: (_xmit_ETHER){+.....}, at: [<ffffffff815072a7>] dev_uc_add+0x27/0x80 [ 43.690575] stack backtrace: [ 43.690970] CPU: 0 PID: 1187 Comm: brctl Not tainted 4.4.0-rc8+ #54 [ 43.691270] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.8.1-20150318_183358- 04/01/2014 [ 43.691770] ffffffff826a25c0 ffff8800369fb8e0 ffffffff81360ceb ffffffff826a25c0 [ 43.692425] ffff8800369fb9b8 ffffffff810d0466 ffff8800369fb968 ffffffff81537139 [ 43.693071] ffff88003a08c880 0000000000000000 00000000ffffffff 0000000002080020 [ 43.693709] Call Trace: [ 43.693931] [<ffffffff81360ceb>] dump_stack+0x4b/0x70 [ 43.694199] [<ffffffff810d0466>] __lock_acquire+0x1e46/0x1e90 [ 43.694483] [<ffffffff81537139>] ? netlink_broadcast_filtered+0x139/0x3e0 [ 43.694789] [<ffffffff8153b5da>] ? nlmsg_notify+0x5a/0xc0 [ 43.695064] [<ffffffff810d10f5>] lock_acquire+0xe5/0x1f0 [ 43.695340] [<ffffffff8150169e>] ? dev_set_rx_mode+0x1e/0x40 [ 43.695623] [<ffffffff815edea5>] _raw_spin_lock_bh+0x45/0x80 [ 43.695901] [<ffffffff8150169e>] ? dev_set_rx_mode+0x1e/0x40 [ 43.696180] [<ffffffff8150169e>] dev_set_rx_mode+0x1e/0x40 [ 43.696460] [<ffffffff8150189c>] dev_set_promiscuity+0x3c/0x50 [ 43.696750] [<ffffffffa0586845>] br_port_set_promisc+0x25/0x50 [bridge] [ 43.697052] [<ffffffffa05869aa>] br_manage_promisc+0x8a/0xe0 [bridge] [ 43.697348] [<ffffffffa05826ee>] br_dev_change_rx_flags+0x1e/0x20 [bridge] [ 43.697655] [<ffffffff81501532>] __dev_set_promiscuity+0x132/0x1f0 [ 43.697943] [<ffffffff81501672>] __dev_set_rx_mode+0x82/0x90 [ 43.698223] [<ffffffff815072de>] dev_uc_add+0x5e/0x80 [ 43.698498] [<ffffffffa05b3c62>] vlan_device_event+0x542/0x650 [8021q] [ 43.698798] [<ffffffff8109886d>] notifier_call_chain+0x5d/0x80 [ 43.699083] [<ffffffff810988b6>] raw_notifier_call_chain+0x16/0x20 [ 43.699374] [<ffffffff814f456e>] call_netdevice_notifiers_info+0x6e/0x80 [ 43.699678] [<ffffffff814f4596>] call_netdevice_notifiers+0x16/0x20 [ 43.699973] [<ffffffffa05872be>] br_add_if+0x47e/0x4c0 [bridge] [ 43.700259] [<ffffffffa058801e>] add_del_if+0x6e/0x80 [bridge] [ 43.700548] [<ffffffffa0588b5f>] br_dev_ioctl+0xaf/0xc0 [bridge] [ 43.700836] [<ffffffff8151a7ac>] dev_ifsioc+0x30c/0x3c0 [ 43.701106] [<ffffffff8151aac9>] dev_ioctl+0xf9/0x6f0 [ 43.701379] [<ffffffff81254345>] ? mntput_no_expire+0x5/0x450 [ 43.701665] [<ffffffff812543ee>] ? mntput_no_expire+0xae/0x450 [ 43.701947] [<ffffffff814d7b02>] sock_do_ioctl+0x42/0x50 [ 43.702219] [<ffffffff814d8175>] sock_ioctl+0x1e5/0x290 [ 43.702500] [<ffffffff81242d0b>] do_vfs_ioctl+0x2cb/0x5c0 [ 43.702771] [<ffffffff81243079>] SyS_ioctl+0x79/0x90 [ 43.703033] [<ffffffff815eebb6>] entry_SYSCALL_64_fastpath+0x16/0x7a CC: Vlad Yasevich <vyasevic@redhat.com> CC: Stephen Hemminger <stephen@networkplumber.org> CC: Bridge list <bridge@lists.linux-foundation.org> CC: Andy Gospodarek <gospo@cumulusnetworks.com> CC: Roopa Prabhu <roopa@cumulusnetworks.com> Fixes: 2796d0c648c9 ("bridge: Automatically manage port promiscuous mode.") Reported-by: Andy Gospodarek <gospo@cumulusnetworks.com> Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-16 02:03:54 +08:00
static struct lock_class_key bridge_netdev_addr_lock_key;
/* net device transmit always called with BH disabled */
netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
const unsigned char *dest = skb->data;
struct net_bridge_fdb_entry *dst;
struct net_bridge_mdb_entry *mdst;
struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
const struct nf_br_ops *nf_ops;
u16 vid = 0;
rcu_read_lock();
nf_ops = rcu_dereference(nf_br_ops);
if (nf_ops && nf_ops->br_dev_xmit_hook(skb)) {
rcu_read_unlock();
return NETDEV_TX_OK;
}
u64_stats_update_begin(&brstats->syncp);
brstats->tx_packets++;
brstats->tx_bytes += skb->len;
u64_stats_update_end(&brstats->syncp);
BR_INPUT_SKB_CB(skb)->brdev = dev;
skb_reset_mac_header(skb);
skb_pull(skb, ETH_HLEN);
if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid))
goto out;
if (is_broadcast_ether_addr(dest)) {
br_flood(br, skb, false, false, true);
} else if (is_multicast_ether_addr(dest)) {
if (unlikely(netpoll_tx_running(dev))) {
br_flood(br, skb, false, false, true);
goto out;
}
if (br_multicast_rcv(br, NULL, skb, vid)) {
kfree_skb(skb);
goto out;
}
mdst = br_mdb_get(br, skb, vid);
if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
br_multicast_querier_exists(br, eth_hdr(skb)))
br_multicast_flood(mdst, skb, false, true);
else
br_flood(br, skb, false, false, true);
} else if ((dst = __br_fdb_get(br, dest, vid)) != NULL) {
br_forward(dst->dst, skb, false, true);
} else {
br_flood(br, skb, true, false, true);
}
out:
rcu_read_unlock();
return NETDEV_TX_OK;
}
bridge: fix lockdep addr_list_lock false positive splat After promisc mode management was introduced a bridge device could do dev_set_promiscuity from its ndo_change_rx_flags() callback which in turn can be called after the bridge's addr_list_lock has been taken (e.g. by dev_uc_add). This causes a false positive lockdep splat because the port interfaces' addr_list_lock is taken when br_manage_promisc() runs after the bridge's addr list lock was already taken. To remove the false positive introduce a custom bridge addr_list_lock class and set it on bridge init. A simple way to reproduce this is with the following: $ brctl addbr br0 $ ip l add l br0 br0.100 type vlan id 100 $ ip l set br0 up $ ip l set br0.100 up $ echo 1 > /sys/class/net/br0/bridge/vlan_filtering $ brctl addif br0 eth0 Splat: [ 43.684325] ============================================= [ 43.684485] [ INFO: possible recursive locking detected ] [ 43.684636] 4.4.0-rc8+ #54 Not tainted [ 43.684755] --------------------------------------------- [ 43.684906] brctl/1187 is trying to acquire lock: [ 43.685047] (_xmit_ETHER){+.....}, at: [<ffffffff8150169e>] dev_set_rx_mode+0x1e/0x40 [ 43.685460] but task is already holding lock: [ 43.685618] (_xmit_ETHER){+.....}, at: [<ffffffff815072a7>] dev_uc_add+0x27/0x80 [ 43.686015] other info that might help us debug this: [ 43.686316] Possible unsafe locking scenario: [ 43.686743] CPU0 [ 43.686967] ---- [ 43.687197] lock(_xmit_ETHER); [ 43.687544] lock(_xmit_ETHER); [ 43.687886] *** DEADLOCK *** [ 43.688438] May be due to missing lock nesting notation [ 43.688882] 2 locks held by brctl/1187: [ 43.689134] #0: (rtnl_mutex){+.+.+.}, at: [<ffffffff81510317>] rtnl_lock+0x17/0x20 [ 43.689852] #1: (_xmit_ETHER){+.....}, at: [<ffffffff815072a7>] dev_uc_add+0x27/0x80 [ 43.690575] stack backtrace: [ 43.690970] CPU: 0 PID: 1187 Comm: brctl Not tainted 4.4.0-rc8+ #54 [ 43.691270] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.8.1-20150318_183358- 04/01/2014 [ 43.691770] ffffffff826a25c0 ffff8800369fb8e0 ffffffff81360ceb ffffffff826a25c0 [ 43.692425] ffff8800369fb9b8 ffffffff810d0466 ffff8800369fb968 ffffffff81537139 [ 43.693071] ffff88003a08c880 0000000000000000 00000000ffffffff 0000000002080020 [ 43.693709] Call Trace: [ 43.693931] [<ffffffff81360ceb>] dump_stack+0x4b/0x70 [ 43.694199] [<ffffffff810d0466>] __lock_acquire+0x1e46/0x1e90 [ 43.694483] [<ffffffff81537139>] ? netlink_broadcast_filtered+0x139/0x3e0 [ 43.694789] [<ffffffff8153b5da>] ? nlmsg_notify+0x5a/0xc0 [ 43.695064] [<ffffffff810d10f5>] lock_acquire+0xe5/0x1f0 [ 43.695340] [<ffffffff8150169e>] ? dev_set_rx_mode+0x1e/0x40 [ 43.695623] [<ffffffff815edea5>] _raw_spin_lock_bh+0x45/0x80 [ 43.695901] [<ffffffff8150169e>] ? dev_set_rx_mode+0x1e/0x40 [ 43.696180] [<ffffffff8150169e>] dev_set_rx_mode+0x1e/0x40 [ 43.696460] [<ffffffff8150189c>] dev_set_promiscuity+0x3c/0x50 [ 43.696750] [<ffffffffa0586845>] br_port_set_promisc+0x25/0x50 [bridge] [ 43.697052] [<ffffffffa05869aa>] br_manage_promisc+0x8a/0xe0 [bridge] [ 43.697348] [<ffffffffa05826ee>] br_dev_change_rx_flags+0x1e/0x20 [bridge] [ 43.697655] [<ffffffff81501532>] __dev_set_promiscuity+0x132/0x1f0 [ 43.697943] [<ffffffff81501672>] __dev_set_rx_mode+0x82/0x90 [ 43.698223] [<ffffffff815072de>] dev_uc_add+0x5e/0x80 [ 43.698498] [<ffffffffa05b3c62>] vlan_device_event+0x542/0x650 [8021q] [ 43.698798] [<ffffffff8109886d>] notifier_call_chain+0x5d/0x80 [ 43.699083] [<ffffffff810988b6>] raw_notifier_call_chain+0x16/0x20 [ 43.699374] [<ffffffff814f456e>] call_netdevice_notifiers_info+0x6e/0x80 [ 43.699678] [<ffffffff814f4596>] call_netdevice_notifiers+0x16/0x20 [ 43.699973] [<ffffffffa05872be>] br_add_if+0x47e/0x4c0 [bridge] [ 43.700259] [<ffffffffa058801e>] add_del_if+0x6e/0x80 [bridge] [ 43.700548] [<ffffffffa0588b5f>] br_dev_ioctl+0xaf/0xc0 [bridge] [ 43.700836] [<ffffffff8151a7ac>] dev_ifsioc+0x30c/0x3c0 [ 43.701106] [<ffffffff8151aac9>] dev_ioctl+0xf9/0x6f0 [ 43.701379] [<ffffffff81254345>] ? mntput_no_expire+0x5/0x450 [ 43.701665] [<ffffffff812543ee>] ? mntput_no_expire+0xae/0x450 [ 43.701947] [<ffffffff814d7b02>] sock_do_ioctl+0x42/0x50 [ 43.702219] [<ffffffff814d8175>] sock_ioctl+0x1e5/0x290 [ 43.702500] [<ffffffff81242d0b>] do_vfs_ioctl+0x2cb/0x5c0 [ 43.702771] [<ffffffff81243079>] SyS_ioctl+0x79/0x90 [ 43.703033] [<ffffffff815eebb6>] entry_SYSCALL_64_fastpath+0x16/0x7a CC: Vlad Yasevich <vyasevic@redhat.com> CC: Stephen Hemminger <stephen@networkplumber.org> CC: Bridge list <bridge@lists.linux-foundation.org> CC: Andy Gospodarek <gospo@cumulusnetworks.com> CC: Roopa Prabhu <roopa@cumulusnetworks.com> Fixes: 2796d0c648c9 ("bridge: Automatically manage port promiscuous mode.") Reported-by: Andy Gospodarek <gospo@cumulusnetworks.com> Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-16 02:03:54 +08:00
static void br_set_lockdep_class(struct net_device *dev)
{
lockdep_set_class(&dev->addr_list_lock, &bridge_netdev_addr_lock_key);
}
static int br_dev_init(struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
int err;
br->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!br->stats)
return -ENOMEM;
err = br_vlan_init(br);
if (err) {
free_percpu(br->stats);
return err;
}
err = br_multicast_init_stats(br);
if (err) {
free_percpu(br->stats);
br_vlan_flush(br);
}
bridge: fix lockdep addr_list_lock false positive splat After promisc mode management was introduced a bridge device could do dev_set_promiscuity from its ndo_change_rx_flags() callback which in turn can be called after the bridge's addr_list_lock has been taken (e.g. by dev_uc_add). This causes a false positive lockdep splat because the port interfaces' addr_list_lock is taken when br_manage_promisc() runs after the bridge's addr list lock was already taken. To remove the false positive introduce a custom bridge addr_list_lock class and set it on bridge init. A simple way to reproduce this is with the following: $ brctl addbr br0 $ ip l add l br0 br0.100 type vlan id 100 $ ip l set br0 up $ ip l set br0.100 up $ echo 1 > /sys/class/net/br0/bridge/vlan_filtering $ brctl addif br0 eth0 Splat: [ 43.684325] ============================================= [ 43.684485] [ INFO: possible recursive locking detected ] [ 43.684636] 4.4.0-rc8+ #54 Not tainted [ 43.684755] --------------------------------------------- [ 43.684906] brctl/1187 is trying to acquire lock: [ 43.685047] (_xmit_ETHER){+.....}, at: [<ffffffff8150169e>] dev_set_rx_mode+0x1e/0x40 [ 43.685460] but task is already holding lock: [ 43.685618] (_xmit_ETHER){+.....}, at: [<ffffffff815072a7>] dev_uc_add+0x27/0x80 [ 43.686015] other info that might help us debug this: [ 43.686316] Possible unsafe locking scenario: [ 43.686743] CPU0 [ 43.686967] ---- [ 43.687197] lock(_xmit_ETHER); [ 43.687544] lock(_xmit_ETHER); [ 43.687886] *** DEADLOCK *** [ 43.688438] May be due to missing lock nesting notation [ 43.688882] 2 locks held by brctl/1187: [ 43.689134] #0: (rtnl_mutex){+.+.+.}, at: [<ffffffff81510317>] rtnl_lock+0x17/0x20 [ 43.689852] #1: (_xmit_ETHER){+.....}, at: [<ffffffff815072a7>] dev_uc_add+0x27/0x80 [ 43.690575] stack backtrace: [ 43.690970] CPU: 0 PID: 1187 Comm: brctl Not tainted 4.4.0-rc8+ #54 [ 43.691270] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.8.1-20150318_183358- 04/01/2014 [ 43.691770] ffffffff826a25c0 ffff8800369fb8e0 ffffffff81360ceb ffffffff826a25c0 [ 43.692425] ffff8800369fb9b8 ffffffff810d0466 ffff8800369fb968 ffffffff81537139 [ 43.693071] ffff88003a08c880 0000000000000000 00000000ffffffff 0000000002080020 [ 43.693709] Call Trace: [ 43.693931] [<ffffffff81360ceb>] dump_stack+0x4b/0x70 [ 43.694199] [<ffffffff810d0466>] __lock_acquire+0x1e46/0x1e90 [ 43.694483] [<ffffffff81537139>] ? netlink_broadcast_filtered+0x139/0x3e0 [ 43.694789] [<ffffffff8153b5da>] ? nlmsg_notify+0x5a/0xc0 [ 43.695064] [<ffffffff810d10f5>] lock_acquire+0xe5/0x1f0 [ 43.695340] [<ffffffff8150169e>] ? dev_set_rx_mode+0x1e/0x40 [ 43.695623] [<ffffffff815edea5>] _raw_spin_lock_bh+0x45/0x80 [ 43.695901] [<ffffffff8150169e>] ? dev_set_rx_mode+0x1e/0x40 [ 43.696180] [<ffffffff8150169e>] dev_set_rx_mode+0x1e/0x40 [ 43.696460] [<ffffffff8150189c>] dev_set_promiscuity+0x3c/0x50 [ 43.696750] [<ffffffffa0586845>] br_port_set_promisc+0x25/0x50 [bridge] [ 43.697052] [<ffffffffa05869aa>] br_manage_promisc+0x8a/0xe0 [bridge] [ 43.697348] [<ffffffffa05826ee>] br_dev_change_rx_flags+0x1e/0x20 [bridge] [ 43.697655] [<ffffffff81501532>] __dev_set_promiscuity+0x132/0x1f0 [ 43.697943] [<ffffffff81501672>] __dev_set_rx_mode+0x82/0x90 [ 43.698223] [<ffffffff815072de>] dev_uc_add+0x5e/0x80 [ 43.698498] [<ffffffffa05b3c62>] vlan_device_event+0x542/0x650 [8021q] [ 43.698798] [<ffffffff8109886d>] notifier_call_chain+0x5d/0x80 [ 43.699083] [<ffffffff810988b6>] raw_notifier_call_chain+0x16/0x20 [ 43.699374] [<ffffffff814f456e>] call_netdevice_notifiers_info+0x6e/0x80 [ 43.699678] [<ffffffff814f4596>] call_netdevice_notifiers+0x16/0x20 [ 43.699973] [<ffffffffa05872be>] br_add_if+0x47e/0x4c0 [bridge] [ 43.700259] [<ffffffffa058801e>] add_del_if+0x6e/0x80 [bridge] [ 43.700548] [<ffffffffa0588b5f>] br_dev_ioctl+0xaf/0xc0 [bridge] [ 43.700836] [<ffffffff8151a7ac>] dev_ifsioc+0x30c/0x3c0 [ 43.701106] [<ffffffff8151aac9>] dev_ioctl+0xf9/0x6f0 [ 43.701379] [<ffffffff81254345>] ? mntput_no_expire+0x5/0x450 [ 43.701665] [<ffffffff812543ee>] ? mntput_no_expire+0xae/0x450 [ 43.701947] [<ffffffff814d7b02>] sock_do_ioctl+0x42/0x50 [ 43.702219] [<ffffffff814d8175>] sock_ioctl+0x1e5/0x290 [ 43.702500] [<ffffffff81242d0b>] do_vfs_ioctl+0x2cb/0x5c0 [ 43.702771] [<ffffffff81243079>] SyS_ioctl+0x79/0x90 [ 43.703033] [<ffffffff815eebb6>] entry_SYSCALL_64_fastpath+0x16/0x7a CC: Vlad Yasevich <vyasevic@redhat.com> CC: Stephen Hemminger <stephen@networkplumber.org> CC: Bridge list <bridge@lists.linux-foundation.org> CC: Andy Gospodarek <gospo@cumulusnetworks.com> CC: Roopa Prabhu <roopa@cumulusnetworks.com> Fixes: 2796d0c648c9 ("bridge: Automatically manage port promiscuous mode.") Reported-by: Andy Gospodarek <gospo@cumulusnetworks.com> Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-16 02:03:54 +08:00
br_set_lockdep_class(dev);
return err;
}
static int br_dev_open(struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
netdev_update_features(dev);
netif_start_queue(dev);
br_stp_enable_bridge(br);
br_multicast_open(br);
return 0;
}
static void br_dev_set_multicast_list(struct net_device *dev)
{
}
bridge: Automatically manage port promiscuous mode. There exist configurations where the administrator or another management entity has the foreknowledge of all the mac addresses of end systems that are being bridged together. In these environments, the administrator can statically configure known addresses in the bridge FDB and disable flooding and learning on ports. This makes it possible to turn off promiscuous mode on the interfaces connected to the bridge. Here is why disabling flooding and learning allows us to control promiscuity: Consider port X. All traffic coming into this port from outside the bridge (ingress) will be either forwarded through other ports of the bridge (egress) or dropped. Forwarding (egress) is defined by FDB entries and by flooding in the event that no FDB entry exists. In the event that flooding is disabled, only FDB entries define the egress. Once learning is disabled, only static FDB entries provided by a management entity define the egress. If we provide information from these static FDBs to the ingress port X, then we'll be able to accept all traffic that can be successfully forwarded and drop all the other traffic sooner without spending CPU cycles to process it. Another way to define the above is as following equations: ingress = egress + drop expanding egress ingress = static FDB + learned FDB + flooding + drop disabling flooding and learning we a left with ingress = static FDB + drop By adding addresses from the static FDB entries to the MAC address filter of an ingress port X, we fully define what the bridge can process without dropping and can thus turn off promiscuous mode, thus dropping packets sooner. There have been suggestions that we may want to allow learning and update the filters with learned addresses as well. This would require mac-level authentication similar to 802.1x to prevent attacks against the hw filters as they are limited resource. Additionally, if the user places the bridge device in promiscuous mode, all ports are placed in promiscuous mode regardless of the changes to flooding and learning. Since the above functionality depends on full static configuration, we have also require that vlan filtering be enabled to take advantage of this. The reason is that the bridge has to be able to receive and process VLAN-tagged frames and the there are only 2 ways to accomplish this right now: promiscuous mode or vlan filtering. Suggested-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-16 21:59:20 +08:00
static void br_dev_change_rx_flags(struct net_device *dev, int change)
{
if (change & IFF_PROMISC)
br_manage_promisc(netdev_priv(dev));
}
static int br_dev_stop(struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
br_stp_disable_bridge(br);
br_multicast_stop(br);
netif_stop_queue(dev);
return 0;
}
static struct rtnl_link_stats64 *br_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *stats)
{
struct net_bridge *br = netdev_priv(dev);
struct pcpu_sw_netstats tmp, sum = { 0 };
unsigned int cpu;
for_each_possible_cpu(cpu) {
unsigned int start;
const struct pcpu_sw_netstats *bstats
= per_cpu_ptr(br->stats, cpu);
do {
start = u64_stats_fetch_begin_irq(&bstats->syncp);
memcpy(&tmp, bstats, sizeof(tmp));
} while (u64_stats_fetch_retry_irq(&bstats->syncp, start));
sum.tx_bytes += tmp.tx_bytes;
sum.tx_packets += tmp.tx_packets;
sum.rx_bytes += tmp.rx_bytes;
sum.rx_packets += tmp.rx_packets;
}
stats->tx_bytes = sum.tx_bytes;
stats->tx_packets = sum.tx_packets;
stats->rx_bytes = sum.rx_bytes;
stats->rx_packets = sum.rx_packets;
return stats;
}
static int br_change_mtu(struct net_device *dev, int new_mtu)
{
struct net_bridge *br = netdev_priv(dev);
if (new_mtu < 68 || new_mtu > br_min_mtu(br))
return -EINVAL;
dev->mtu = new_mtu;
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
/* remember the MTU in the rtable for PMTU */
dst_metric_set(&br->fake_rtable.dst, RTAX_MTU, new_mtu);
#endif
return 0;
}
/* Allow setting mac address to any valid ethernet address. */
static int br_set_mac_address(struct net_device *dev, void *p)
{
struct net_bridge *br = netdev_priv(dev);
struct sockaddr *addr = p;
if (!is_valid_ether_addr(addr->sa_data))
return -EADDRNOTAVAIL;
spin_lock_bh(&br->lock);
if (!ether_addr_equal(dev->dev_addr, addr->sa_data)) {
/* Mac address will be changed in br_stp_change_bridge_id(). */
br_stp_change_bridge_id(br, addr->sa_data);
}
spin_unlock_bh(&br->lock);
return 0;
}
static void br_getinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
strlcpy(info->driver, "bridge", sizeof(info->driver));
strlcpy(info->version, BR_VERSION, sizeof(info->version));
strlcpy(info->fw_version, "N/A", sizeof(info->fw_version));
strlcpy(info->bus_info, "N/A", sizeof(info->bus_info));
}
static netdev_features_t br_fix_features(struct net_device *dev,
netdev_features_t features)
{
struct net_bridge *br = netdev_priv(dev);
return br_features_recompute(br, features);
}
#ifdef CONFIG_NET_POLL_CONTROLLER
static void br_poll_controller(struct net_device *br_dev)
{
}
static void br_netpoll_cleanup(struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
struct net_bridge_port *p;
list_for_each_entry(p, &br->port_list, list)
br_netpoll_disable(p);
}
netpoll: Remove gfp parameter from __netpoll_setup The gfp parameter was added in: commit 47be03a28cc6c80e3aa2b3e8ed6d960ff0c5c0af Author: Amerigo Wang <amwang@redhat.com> Date: Fri Aug 10 01:24:37 2012 +0000 netpoll: use GFP_ATOMIC in slave_enable_netpoll() and __netpoll_setup() slave_enable_netpoll() and __netpoll_setup() may be called with read_lock() held, so should use GFP_ATOMIC to allocate memory. Eric suggested to pass gfp flags to __netpoll_setup(). Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: "David S. Miller" <davem@davemloft.net> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Cong Wang <amwang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net> The reason for the gfp parameter was removed in: commit c4cdef9b7183159c23c7302aaf270d64c549f557 Author: dingtianhong <dingtianhong@huawei.com> Date: Tue Jul 23 15:25:27 2013 +0800 bonding: don't call slave_xxx_netpoll under spinlocks The slave_xxx_netpoll will call synchronize_rcu_bh(), so the function may schedule and sleep, it should't be called under spinlocks. bond_netpoll_setup() and bond_netpoll_cleanup() are always protected by rtnl lock, it is no need to take the read lock, as the slave list couldn't be changed outside rtnl lock. Signed-off-by: Ding Tianhong <dingtianhong@huawei.com> Cc: Jay Vosburgh <fubar@us.ibm.com> Cc: Andy Gospodarek <andy@greyhouse.net> Signed-off-by: David S. Miller <davem@davemloft.net> Nothing else that calls __netpoll_setup or ndo_netpoll_setup requires a gfp paramter, so remove the gfp parameter from both of these functions making the code clearer. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-28 06:36:38 +08:00
static int __br_netpoll_enable(struct net_bridge_port *p)
{
struct netpoll *np;
int err;
netpoll: Remove gfp parameter from __netpoll_setup The gfp parameter was added in: commit 47be03a28cc6c80e3aa2b3e8ed6d960ff0c5c0af Author: Amerigo Wang <amwang@redhat.com> Date: Fri Aug 10 01:24:37 2012 +0000 netpoll: use GFP_ATOMIC in slave_enable_netpoll() and __netpoll_setup() slave_enable_netpoll() and __netpoll_setup() may be called with read_lock() held, so should use GFP_ATOMIC to allocate memory. Eric suggested to pass gfp flags to __netpoll_setup(). Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: "David S. Miller" <davem@davemloft.net> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Cong Wang <amwang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net> The reason for the gfp parameter was removed in: commit c4cdef9b7183159c23c7302aaf270d64c549f557 Author: dingtianhong <dingtianhong@huawei.com> Date: Tue Jul 23 15:25:27 2013 +0800 bonding: don't call slave_xxx_netpoll under spinlocks The slave_xxx_netpoll will call synchronize_rcu_bh(), so the function may schedule and sleep, it should't be called under spinlocks. bond_netpoll_setup() and bond_netpoll_cleanup() are always protected by rtnl lock, it is no need to take the read lock, as the slave list couldn't be changed outside rtnl lock. Signed-off-by: Ding Tianhong <dingtianhong@huawei.com> Cc: Jay Vosburgh <fubar@us.ibm.com> Cc: Andy Gospodarek <andy@greyhouse.net> Signed-off-by: David S. Miller <davem@davemloft.net> Nothing else that calls __netpoll_setup or ndo_netpoll_setup requires a gfp paramter, so remove the gfp parameter from both of these functions making the code clearer. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-28 06:36:38 +08:00
np = kzalloc(sizeof(*p->np), GFP_KERNEL);
if (!np)
return -ENOMEM;
netpoll: Remove gfp parameter from __netpoll_setup The gfp parameter was added in: commit 47be03a28cc6c80e3aa2b3e8ed6d960ff0c5c0af Author: Amerigo Wang <amwang@redhat.com> Date: Fri Aug 10 01:24:37 2012 +0000 netpoll: use GFP_ATOMIC in slave_enable_netpoll() and __netpoll_setup() slave_enable_netpoll() and __netpoll_setup() may be called with read_lock() held, so should use GFP_ATOMIC to allocate memory. Eric suggested to pass gfp flags to __netpoll_setup(). Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: "David S. Miller" <davem@davemloft.net> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Cong Wang <amwang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net> The reason for the gfp parameter was removed in: commit c4cdef9b7183159c23c7302aaf270d64c549f557 Author: dingtianhong <dingtianhong@huawei.com> Date: Tue Jul 23 15:25:27 2013 +0800 bonding: don't call slave_xxx_netpoll under spinlocks The slave_xxx_netpoll will call synchronize_rcu_bh(), so the function may schedule and sleep, it should't be called under spinlocks. bond_netpoll_setup() and bond_netpoll_cleanup() are always protected by rtnl lock, it is no need to take the read lock, as the slave list couldn't be changed outside rtnl lock. Signed-off-by: Ding Tianhong <dingtianhong@huawei.com> Cc: Jay Vosburgh <fubar@us.ibm.com> Cc: Andy Gospodarek <andy@greyhouse.net> Signed-off-by: David S. Miller <davem@davemloft.net> Nothing else that calls __netpoll_setup or ndo_netpoll_setup requires a gfp paramter, so remove the gfp parameter from both of these functions making the code clearer. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-28 06:36:38 +08:00
err = __netpoll_setup(np, p->dev);
if (err) {
kfree(np);
return err;
}
p->np = np;
return err;
}
netpoll: Remove gfp parameter from __netpoll_setup The gfp parameter was added in: commit 47be03a28cc6c80e3aa2b3e8ed6d960ff0c5c0af Author: Amerigo Wang <amwang@redhat.com> Date: Fri Aug 10 01:24:37 2012 +0000 netpoll: use GFP_ATOMIC in slave_enable_netpoll() and __netpoll_setup() slave_enable_netpoll() and __netpoll_setup() may be called with read_lock() held, so should use GFP_ATOMIC to allocate memory. Eric suggested to pass gfp flags to __netpoll_setup(). Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: "David S. Miller" <davem@davemloft.net> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Cong Wang <amwang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net> The reason for the gfp parameter was removed in: commit c4cdef9b7183159c23c7302aaf270d64c549f557 Author: dingtianhong <dingtianhong@huawei.com> Date: Tue Jul 23 15:25:27 2013 +0800 bonding: don't call slave_xxx_netpoll under spinlocks The slave_xxx_netpoll will call synchronize_rcu_bh(), so the function may schedule and sleep, it should't be called under spinlocks. bond_netpoll_setup() and bond_netpoll_cleanup() are always protected by rtnl lock, it is no need to take the read lock, as the slave list couldn't be changed outside rtnl lock. Signed-off-by: Ding Tianhong <dingtianhong@huawei.com> Cc: Jay Vosburgh <fubar@us.ibm.com> Cc: Andy Gospodarek <andy@greyhouse.net> Signed-off-by: David S. Miller <davem@davemloft.net> Nothing else that calls __netpoll_setup or ndo_netpoll_setup requires a gfp paramter, so remove the gfp parameter from both of these functions making the code clearer. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-28 06:36:38 +08:00
int br_netpoll_enable(struct net_bridge_port *p)
{
if (!p->br->dev->npinfo)
return 0;
netpoll: Remove gfp parameter from __netpoll_setup The gfp parameter was added in: commit 47be03a28cc6c80e3aa2b3e8ed6d960ff0c5c0af Author: Amerigo Wang <amwang@redhat.com> Date: Fri Aug 10 01:24:37 2012 +0000 netpoll: use GFP_ATOMIC in slave_enable_netpoll() and __netpoll_setup() slave_enable_netpoll() and __netpoll_setup() may be called with read_lock() held, so should use GFP_ATOMIC to allocate memory. Eric suggested to pass gfp flags to __netpoll_setup(). Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: "David S. Miller" <davem@davemloft.net> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Cong Wang <amwang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net> The reason for the gfp parameter was removed in: commit c4cdef9b7183159c23c7302aaf270d64c549f557 Author: dingtianhong <dingtianhong@huawei.com> Date: Tue Jul 23 15:25:27 2013 +0800 bonding: don't call slave_xxx_netpoll under spinlocks The slave_xxx_netpoll will call synchronize_rcu_bh(), so the function may schedule and sleep, it should't be called under spinlocks. bond_netpoll_setup() and bond_netpoll_cleanup() are always protected by rtnl lock, it is no need to take the read lock, as the slave list couldn't be changed outside rtnl lock. Signed-off-by: Ding Tianhong <dingtianhong@huawei.com> Cc: Jay Vosburgh <fubar@us.ibm.com> Cc: Andy Gospodarek <andy@greyhouse.net> Signed-off-by: David S. Miller <davem@davemloft.net> Nothing else that calls __netpoll_setup or ndo_netpoll_setup requires a gfp paramter, so remove the gfp parameter from both of these functions making the code clearer. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-28 06:36:38 +08:00
return __br_netpoll_enable(p);
}
netpoll: Remove gfp parameter from __netpoll_setup The gfp parameter was added in: commit 47be03a28cc6c80e3aa2b3e8ed6d960ff0c5c0af Author: Amerigo Wang <amwang@redhat.com> Date: Fri Aug 10 01:24:37 2012 +0000 netpoll: use GFP_ATOMIC in slave_enable_netpoll() and __netpoll_setup() slave_enable_netpoll() and __netpoll_setup() may be called with read_lock() held, so should use GFP_ATOMIC to allocate memory. Eric suggested to pass gfp flags to __netpoll_setup(). Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: "David S. Miller" <davem@davemloft.net> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Cong Wang <amwang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net> The reason for the gfp parameter was removed in: commit c4cdef9b7183159c23c7302aaf270d64c549f557 Author: dingtianhong <dingtianhong@huawei.com> Date: Tue Jul 23 15:25:27 2013 +0800 bonding: don't call slave_xxx_netpoll under spinlocks The slave_xxx_netpoll will call synchronize_rcu_bh(), so the function may schedule and sleep, it should't be called under spinlocks. bond_netpoll_setup() and bond_netpoll_cleanup() are always protected by rtnl lock, it is no need to take the read lock, as the slave list couldn't be changed outside rtnl lock. Signed-off-by: Ding Tianhong <dingtianhong@huawei.com> Cc: Jay Vosburgh <fubar@us.ibm.com> Cc: Andy Gospodarek <andy@greyhouse.net> Signed-off-by: David S. Miller <davem@davemloft.net> Nothing else that calls __netpoll_setup or ndo_netpoll_setup requires a gfp paramter, so remove the gfp parameter from both of these functions making the code clearer. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-28 06:36:38 +08:00
static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni)
{
struct net_bridge *br = netdev_priv(dev);
struct net_bridge_port *p;
int err = 0;
list_for_each_entry(p, &br->port_list, list) {
if (!p->dev)
continue;
netpoll: Remove gfp parameter from __netpoll_setup The gfp parameter was added in: commit 47be03a28cc6c80e3aa2b3e8ed6d960ff0c5c0af Author: Amerigo Wang <amwang@redhat.com> Date: Fri Aug 10 01:24:37 2012 +0000 netpoll: use GFP_ATOMIC in slave_enable_netpoll() and __netpoll_setup() slave_enable_netpoll() and __netpoll_setup() may be called with read_lock() held, so should use GFP_ATOMIC to allocate memory. Eric suggested to pass gfp flags to __netpoll_setup(). Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: "David S. Miller" <davem@davemloft.net> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Cong Wang <amwang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net> The reason for the gfp parameter was removed in: commit c4cdef9b7183159c23c7302aaf270d64c549f557 Author: dingtianhong <dingtianhong@huawei.com> Date: Tue Jul 23 15:25:27 2013 +0800 bonding: don't call slave_xxx_netpoll under spinlocks The slave_xxx_netpoll will call synchronize_rcu_bh(), so the function may schedule and sleep, it should't be called under spinlocks. bond_netpoll_setup() and bond_netpoll_cleanup() are always protected by rtnl lock, it is no need to take the read lock, as the slave list couldn't be changed outside rtnl lock. Signed-off-by: Ding Tianhong <dingtianhong@huawei.com> Cc: Jay Vosburgh <fubar@us.ibm.com> Cc: Andy Gospodarek <andy@greyhouse.net> Signed-off-by: David S. Miller <davem@davemloft.net> Nothing else that calls __netpoll_setup or ndo_netpoll_setup requires a gfp paramter, so remove the gfp parameter from both of these functions making the code clearer. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-28 06:36:38 +08:00
err = __br_netpoll_enable(p);
if (err)
goto fail;
}
out:
return err;
fail:
br_netpoll_cleanup(dev);
goto out;
}
void br_netpoll_disable(struct net_bridge_port *p)
{
struct netpoll *np = p->np;
if (!np)
return;
p->np = NULL;
__netpoll_free_async(np);
}
#endif
static int br_add_slave(struct net_device *dev, struct net_device *slave_dev)
{
struct net_bridge *br = netdev_priv(dev);
return br_add_if(br, slave_dev);
}
static int br_del_slave(struct net_device *dev, struct net_device *slave_dev)
{
struct net_bridge *br = netdev_priv(dev);
return br_del_if(br, slave_dev);
}
static const struct ethtool_ops br_ethtool_ops = {
.get_drvinfo = br_getinfo,
.get_link = ethtool_op_get_link,
};
static const struct net_device_ops br_netdev_ops = {
.ndo_open = br_dev_open,
.ndo_stop = br_dev_stop,
.ndo_init = br_dev_init,
.ndo_start_xmit = br_dev_xmit,
.ndo_get_stats64 = br_get_stats64,
.ndo_set_mac_address = br_set_mac_address,
.ndo_set_rx_mode = br_dev_set_multicast_list,
bridge: Automatically manage port promiscuous mode. There exist configurations where the administrator or another management entity has the foreknowledge of all the mac addresses of end systems that are being bridged together. In these environments, the administrator can statically configure known addresses in the bridge FDB and disable flooding and learning on ports. This makes it possible to turn off promiscuous mode on the interfaces connected to the bridge. Here is why disabling flooding and learning allows us to control promiscuity: Consider port X. All traffic coming into this port from outside the bridge (ingress) will be either forwarded through other ports of the bridge (egress) or dropped. Forwarding (egress) is defined by FDB entries and by flooding in the event that no FDB entry exists. In the event that flooding is disabled, only FDB entries define the egress. Once learning is disabled, only static FDB entries provided by a management entity define the egress. If we provide information from these static FDBs to the ingress port X, then we'll be able to accept all traffic that can be successfully forwarded and drop all the other traffic sooner without spending CPU cycles to process it. Another way to define the above is as following equations: ingress = egress + drop expanding egress ingress = static FDB + learned FDB + flooding + drop disabling flooding and learning we a left with ingress = static FDB + drop By adding addresses from the static FDB entries to the MAC address filter of an ingress port X, we fully define what the bridge can process without dropping and can thus turn off promiscuous mode, thus dropping packets sooner. There have been suggestions that we may want to allow learning and update the filters with learned addresses as well. This would require mac-level authentication similar to 802.1x to prevent attacks against the hw filters as they are limited resource. Additionally, if the user places the bridge device in promiscuous mode, all ports are placed in promiscuous mode regardless of the changes to flooding and learning. Since the above functionality depends on full static configuration, we have also require that vlan filtering be enabled to take advantage of this. The reason is that the bridge has to be able to receive and process VLAN-tagged frames and the there are only 2 ways to accomplish this right now: promiscuous mode or vlan filtering. Suggested-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-16 21:59:20 +08:00
.ndo_change_rx_flags = br_dev_change_rx_flags,
.ndo_change_mtu = br_change_mtu,
.ndo_do_ioctl = br_dev_ioctl,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_netpoll_setup = br_netpoll_setup,
.ndo_netpoll_cleanup = br_netpoll_cleanup,
.ndo_poll_controller = br_poll_controller,
#endif
.ndo_add_slave = br_add_slave,
.ndo_del_slave = br_del_slave,
.ndo_fix_features = br_fix_features,
.ndo_neigh_construct = netdev_default_l2upper_neigh_construct,
.ndo_neigh_destroy = netdev_default_l2upper_neigh_destroy,
net: add generic PF_BRIDGE:RTM_ FDB hooks This adds two new flags NTF_MASTER and NTF_SELF that can now be used to specify where PF_BRIDGE netlink commands should be sent. NTF_MASTER sends the commands to the 'dev->master' device for parsing. Typically this will be the linux net/bridge, or open-vswitch devices. Also without any flags set the command will be handled by the master device as well so that current user space tools continue to work as expected. The NTF_SELF flag will push the PF_BRIDGE commands to the device. In the basic example below the commands are then parsed and programmed in the embedded bridge. Note if both NTF_SELF and NTF_MASTER bits are set then the command will be sent to both 'dev->master' and 'dev' this allows user space to easily keep the embedded bridge and software bridge in sync. There is a slight complication in the case with both flags set when an error occurs. To resolve this the rtnl handler clears the NTF_ flag in the netlink ack to indicate which sets completed successfully. The add/del handlers will abort as soon as any error occurs. To support this new net device ops were added to call into the device and the existing bridging code was refactored to use these. There should be no required changes in user space to support the current bridge behavior. A basic setup with a SR-IOV enabled NIC looks like this, veth0 veth2 | | ------------ | bridge0 | <---- software bridging ------------ / / ethx.y ethx VF PF \ \ <---- propagate FDB entries to HW \ \ -------------------- | Embedded Bridge | <---- hardware offloaded switching -------------------- In this case the embedded bridge must be managed to allow 'veth0' to communicate with 'ethx.y' correctly. At present drivers managing the embedded bridge either send frames onto the network which then get dropped by the switch OR the embedded bridge will flood these frames. With this patch we have a mechanism to manage the embedded bridge correctly from user space. This example is specific to SR-IOV but replacing the VF with another PF or dropping this into the DSA framework generates similar management issues. Examples session using the 'br'[1] tool to add, dump and then delete a mac address with a new "embedded" option and enabled ixgbe driver: # br fdb add 22:35:19:ac:60:59 dev eth3 # br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static #br fdb add 22:35:19:ac:60:59 embedded dev eth3 #br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static eth3 22:35:19:ac:60:59 local embedded #br fdb del 22:35:19:ac:60:59 embedded dev eth3 I added a couple lines to 'br' to set the flags correctly is all. It is my opinion that the merit of this patch is now embedded and SW bridges can both be modeled correctly in user space using very nearly the same message passing. [1] 'br' tool was published as an RFC here and will be renamed 'bridge' http://patchwork.ozlabs.org/patch/117664/ Thanks to Jamal Hadi Salim, Stephen Hemminger and Ben Hutchings for valuable feedback, suggestions, and review. v2: fixed api descriptions and error case with both NTF_SELF and NTF_MASTER set plus updated patch description. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-15 14:43:56 +08:00
.ndo_fdb_add = br_fdb_add,
.ndo_fdb_del = br_fdb_delete,
.ndo_fdb_dump = br_fdb_dump,
.ndo_bridge_getlink = br_getlink,
.ndo_bridge_setlink = br_setlink,
.ndo_bridge_dellink = br_dellink,
.ndo_features_check = passthru_features_check,
};
static void br_dev_free(struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
free_percpu(br->stats);
free_netdev(dev);
}
static struct device_type br_type = {
.name = "bridge",
};
void br_dev_setup(struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
eth_hw_addr_random(dev);
ether_setup(dev);
dev->netdev_ops = &br_netdev_ops;
dev->destructor = br_dev_free;
dev->ethtool_ops = &br_ethtool_ops;
SET_NETDEV_DEVTYPE(dev, &br_type);
dev->priv_flags = IFF_EBRIDGE | IFF_NO_QUEUE;
dev->features = COMMON_FEATURES | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL |
NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX;
dev->vlan_features = COMMON_FEATURES;
br->dev = dev;
spin_lock_init(&br->lock);
INIT_LIST_HEAD(&br->port_list);
spin_lock_init(&br->hash_lock);
br->bridge_id.prio[0] = 0x80;
br->bridge_id.prio[1] = 0x00;
ether_addr_copy(br->group_addr, eth_reserved_addr_base);
br->stp_enabled = BR_NO_STP;
br->group_fwd_mask = BR_GROUPFWD_DEFAULT;
br->group_fwd_mask_required = BR_GROUPFWD_DEFAULT;
br->designated_root = br->bridge_id;
br->bridge_max_age = br->max_age = 20 * HZ;
br->bridge_hello_time = br->hello_time = 2 * HZ;
br->bridge_forward_delay = br->forward_delay = 15 * HZ;
br->ageing_time = BR_DEFAULT_AGEING_TIME;
br_netfilter_rtable_init(br);
br_stp_timer_init(br);
br_multicast_init(br);
}